1 files changed, 64 insertions, 36 deletions

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 92c02c886fe7..2e61ac137128 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -49,7 +49,8 @@ EXPORT_SYMBOL(ip6tun_encaps);
 
 void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 proto,
-		   __u8 tos, __u8 ttl, __be16 df, bool xnet)
+		   __u8 tos, __u8 ttl, __be16 df, bool xnet,
+		   u16 ipcb_flags)
 {
 	int pkt_len = skb->len - skb_inner_network_offset(skb);
 	struct net *net = dev_net(rt->dst.dev);
@@ -62,6 +63,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	skb_clear_hash_if_not_l4(skb);
 	skb_dst_set(skb, &rt->dst);
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	IPCB(skb)->flags = ipcb_flags;
 
 	/* Push down and install the IP header. */
 	skb_push(skb, sizeof(struct iphdr));
@@ -125,6 +127,7 @@ EXPORT_SYMBOL_GPL(__iptunnel_pull_header);
 struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 					     gfp_t flags)
 {
+	IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { };
 	struct metadata_dst *res;
 	struct ip_tunnel_info *dst, *src;
 
@@ -144,10 +147,10 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 		       sizeof(struct in6_addr));
 	else
 		dst->key.u.ipv4.dst = src->key.u.ipv4.src;
-	dst->key.tun_flags = src->key.tun_flags;
+	ip_tunnel_flags_copy(dst->key.tun_flags, src->key.tun_flags);
 	dst->mode = src->mode | IP_TUNNEL_INFO_TX;
 	ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src),
-				src->options_len, 0);
+				src->options_len, tun_flags);
 
 	return res;
 }
@@ -203,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);
@@ -224,7 +230,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 		.un.frag.__unused	= 0,
 		.un.frag.mtu		= htons(mtu),
 	};
-	icmph->checksum = ip_compute_csum(icmph, len);
+	icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0));
 	skb_reset_transport_header(skb);
 
 	niph = skb_push(skb, sizeof(*niph));
@@ -297,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);
@@ -332,7 +341,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	};
 	skb_reset_network_header(skb);
 
-	csum = csum_partial(icmp6h, len, 0);
+	csum = skb_checksum(skb, skb_transport_offset(skb), len, 0);
 	icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len,
 					      IPPROTO_ICMPV6, csum);
 
@@ -415,7 +424,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-	if (!reply || skb->pkt_type == PACKET_HOST)
+	if (!reply)
 		return 0;
 
 	if (skb->protocol == htons(ETH_P_IP))
@@ -450,7 +459,7 @@ static const struct nla_policy
 geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
 	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static const struct nla_policy
@@ -497,7 +506,7 @@ static int ip_tun_parse_opts_geneve(struct nlattr *attr,
 		opt->opt_class = nla_get_be16(attr);
 		attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE];
 		opt->type = nla_get_u8(attr);
-		info->key.tun_flags |= TUNNEL_GENEVE_OPT;
+		__set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags);
 	}
 
 	return sizeof(struct geneve_opt) + data_len;
@@ -525,7 +534,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr,
 		attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP];
 		md->gbp = nla_get_u32(attr);
 		md->gbp &= VXLAN_GBP_MASK;
-		info->key.tun_flags |= TUNNEL_VXLAN_OPT;
+		__set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags);
 	}
 
 	return sizeof(struct vxlan_metadata);
@@ -574,7 +583,7 @@ static int ip_tun_parse_opts_erspan(struct nlattr *attr,
 			set_hwid(&md->u.md2, nla_get_u8(attr));
 		}
 
-		info->key.tun_flags |= TUNNEL_ERSPAN_OPT;
+		__set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags);
 	}
 
 	return sizeof(struct erspan_metadata);
@@ -585,7 +594,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
 {
 	int err, rem, opt_len, opts_len = 0;
 	struct nlattr *nla;
-	__be16 type = 0;
+	u32 type = 0;
 
 	if (!attr)
 		return 0;
@@ -598,7 +607,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
 	nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) {
 		switch (nla_type(nla)) {
 		case LWTUNNEL_IP_OPTS_GENEVE:
-			if (type && type != TUNNEL_GENEVE_OPT)
+			if (type && type != IP_TUNNEL_GENEVE_OPT_BIT)
 				return -EINVAL;
 			opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len,
 							   extack);
@@ -607,7 +616,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
 			opts_len += opt_len;
 			if (opts_len > IP_TUNNEL_OPTS_MAX)
 				return -EINVAL;
-			type = TUNNEL_GENEVE_OPT;
+			type = IP_TUNNEL_GENEVE_OPT_BIT;
 			break;
 		case LWTUNNEL_IP_OPTS_VXLAN:
 			if (type)
@@ -617,7 +626,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
 			if (opt_len < 0)
 				return opt_len;
 			opts_len += opt_len;
-			type = TUNNEL_VXLAN_OPT;
+			type = IP_TUNNEL_VXLAN_OPT_BIT;
 			break;
 		case LWTUNNEL_IP_OPTS_ERSPAN:
 			if (type)
@@ -627,7 +636,7 @@ static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info,
 			if (opt_len < 0)
 				return opt_len;
 			opts_len += opt_len;
-			type = TUNNEL_ERSPAN_OPT;
+			type = IP_TUNNEL_ERSPAN_OPT_BIT;
 			break;
 		default:
 			return -EINVAL;
@@ -705,10 +714,16 @@ static int ip_tun_build_state(struct net *net, struct nlattr *attr,
 	if (tb[LWTUNNEL_IP_TOS])
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
 
-	if (tb[LWTUNNEL_IP_FLAGS])
-		tun_info->key.tun_flags |=
-				(nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) &
-				 ~TUNNEL_OPTIONS_PRESENT);
+	if (tb[LWTUNNEL_IP_FLAGS]) {
+		IP_TUNNEL_DECLARE_FLAGS(flags);
+
+		ip_tunnel_flags_from_be16(flags,
+					  nla_get_be16(tb[LWTUNNEL_IP_FLAGS]));
+		ip_tunnel_clear_options_present(flags);
+
+		ip_tunnel_flags_or(tun_info->key.tun_flags,
+				   tun_info->key.tun_flags, flags);
+	}
 
 	tun_info->mode = IP_TUNNEL_INFO_TX;
 	tun_info->options_len = opt_len;
@@ -812,18 +827,18 @@ static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type,
 	struct nlattr *nest;
 	int err = 0;
 
-	if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+	if (!ip_tunnel_is_options_present(tun_info->key.tun_flags))
 		return 0;
 
 	nest = nla_nest_start_noflag(skb, type);
 	if (!nest)
 		return -ENOMEM;
 
-	if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT)
+	if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_info->key.tun_flags))
 		err = ip_tun_fill_encap_opts_geneve(skb, tun_info);
-	else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT)
+	else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_info->key.tun_flags))
 		err = ip_tun_fill_encap_opts_vxlan(skb, tun_info);
-	else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)
+	else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_info->key.tun_flags))
 		err = ip_tun_fill_encap_opts_erspan(skb, tun_info);
 
 	if (err) {
@@ -846,7 +861,8 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
-	    nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) ||
+	    nla_put_be16(skb, LWTUNNEL_IP_FLAGS,
+			 ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) ||
 	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info))
 		return -ENOMEM;
 
@@ -857,11 +873,11 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
 {
 	int opt_len;
 
-	if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT))
+	if (!ip_tunnel_is_options_present(info->key.tun_flags))
 		return 0;
 
 	opt_len = nla_total_size(0);		/* LWTUNNEL_IP_OPTS */
-	if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+	if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) {
 		struct geneve_opt *opt;
 		int offset = 0;
 
@@ -874,10 +890,10 @@ static int ip_tun_opts_nlsize(struct ip_tunnel_info *info)
 							/* OPT_GENEVE_DATA */
 			offset += sizeof(*opt) + opt->length * 4;
 		}
-	} else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+	} else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) {
 		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_VXLAN */
 			   + nla_total_size(4);	/* OPT_VXLAN_GBP */
-	} else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) {
+	} else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) {
 		struct erspan_metadata *md = ip_tunnel_info_opts(info);
 
 		opt_len += nla_total_size(0)	/* LWTUNNEL_IP_OPTS_ERSPAN */
@@ -984,10 +1000,17 @@ static int ip6_tun_build_state(struct net *net, struct nlattr *attr,
 	if (tb[LWTUNNEL_IP6_TC])
 		tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
 
-	if (tb[LWTUNNEL_IP6_FLAGS])
-		tun_info->key.tun_flags |=
-				(nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) &
-				 ~TUNNEL_OPTIONS_PRESENT);
+	if (tb[LWTUNNEL_IP6_FLAGS]) {
+		IP_TUNNEL_DECLARE_FLAGS(flags);
+		__be16 data;
+
+		data = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
+		ip_tunnel_flags_from_be16(flags, data);
+		ip_tunnel_clear_options_present(flags);
+
+		ip_tunnel_flags_or(tun_info->key.tun_flags,
+				   tun_info->key.tun_flags, flags);
+	}
 
 	tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
 	tun_info->options_len = opt_len;
@@ -1008,7 +1031,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb,
 	    nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
 	    nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
-	    nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) ||
+	    nla_put_be16(skb, LWTUNNEL_IP6_FLAGS,
+			 ip_tunnel_flags_to_be16(tun_info->key.tun_flags)) ||
 	    ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info))
 		return -ENOMEM;
 
@@ -1116,7 +1140,7 @@ bool ip_tunnel_netlink_encap_parms(struct nlattr *data[],
 EXPORT_SYMBOL_GPL(ip_tunnel_netlink_encap_parms);
 
 void ip_tunnel_netlink_parms(struct nlattr *data[],
-			     struct ip_tunnel_parm *parms)
+			     struct ip_tunnel_parm_kern *parms)
 {
 	if (data[IFLA_IPTUN_LINK])
 		parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
@@ -1139,8 +1163,12 @@ void ip_tunnel_netlink_parms(struct nlattr *data[],
 	if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
 		parms->iph.frag_off = htons(IP_DF);
 
-	if (data[IFLA_IPTUN_FLAGS])
-		parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
+	if (data[IFLA_IPTUN_FLAGS]) {
+		__be16 flags;
+
+		flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]);
+		ip_tunnel_flags_from_be16(parms->i_flags, flags);
+	}
 
 	if (data[IFLA_IPTUN_PROTO])
 		parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);